{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T02:02:59Z","timestamp":1782871379215,"version":"3.54.5"},"reference-count":54,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Physiol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Melasma is a common acquired facial hyperpigmentation disorder characterized by symmetrical brown patches, often occurring in the zygomatic region, forehead, and upper lip. Its blurred boundaries, color similarity to normal skin, and irregular morphology\u2014combined with lighting variability and skin reflections\u2014pose significant challenges for automated lesion segmentation. This study aims to develop an effective and lightweight deep learning model tailored for accurate melasma segmentation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose a novel lightweight segmentation network, HHBSNet, specifically designed for melasma lesion analysis. The model incorporates a Global Channel-Spatial Attention (GCSA) module that jointly leverages channel and spatial attention to suppress lighting interference and enhance feature discrimination in low-contrast, irregular boundaries. In addition, a Multiscale Cavity Fusion (MCF) module is introduced to extend the receptive field via multi-dilation rates, enabling effective capture of lesions at various scales without reducing resolution. The network further integrates local-global semantic fusion and adopts a combined loss strategy of cross-entropy and focal loss to address class imbalance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>HHBSNet was evaluated on a self-constructed dataset comprising 501 practical facial melasma images. Quantitative results demonstrate that HHBSNet outperforms existing mainstream segmentation methods, achieving a mean Intersection over Union (Miou) of 79.69%, accuracy (ACC) of 96.68%, F-score of 88.10%, recall of 88.18%, and precision of 87.80%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed HHBSNet demonstrates superior segmentation performance and robustness in handling melasma\u2019s challenging visual characteristics. Its lightweight structure and strong generalization ability suggest promising potential for application in computer-aided diagnosis and large-scale clinical screening of facial pigmentary disorders.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphys.2025.1665138","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T05:21:37Z","timestamp":1762320097000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["HHBSNet: a global channel\u2013spatial attention and multi\u2010scale dilated convolution network for automatic melasma segmentation"],"prefix":"10.3389","volume":"16","author":[{"given":"Shange","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linshuai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcin","family":"Grzegorzek","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"290","DOI":"10.2166\/wqrj.2019.048","article-title":"Development of PANI\/BN-based absorbents for water remediation","volume":"54","author":"Arsalan","year":"2019","journal-title":"Water Qual. Res. J."},{"key":"B2","doi-asserted-by":"publisher","first-page":"105486","DOI":"10.1016\/j.microc.2020.105486","article-title":"Preparation and comparison of colloid based Ni50Co50 (OH) 2\/BOX electrocatalyst for catalysis and high performance nonenzymatic glucose sensor","volume":"159","author":"Arsalan","year":"2020","journal-title":"Microchem. J."},{"key":"B3","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1002\/elan.202060166","article-title":"Rational design of highly efficient one\u2010pot synthesis of ternary PtNiCo\/FTO nanocatalyst for hydroquinone and catechol sensing","volume":"33","author":"Awais","year":"2021","journal-title":"Electroanalysis"},{"key":"B4","doi-asserted-by":"publisher","first-page":"572","DOI":"10.1046\/j.1365-2133.2003.05419.x","article-title":"Development and validation of a health\u2010related quality of life instrument for women with melasma","volume":"149","author":"Balkrishnan","year":"2003","journal-title":"Br. J. Dermatology"},{"key":"B5","volume-title":"Ma-unet: an improved version of unet based on multi-scale and attention mechanism for medical image segmentation: third international conference on electronics and communication; network and computer technology (ECNCT 2021)","author":"Cai","year":"2022"},{"key":"B6","volume-title":"Swin-unet: unet-like pure transformer for medical image segmentation: european conference on computer vision","author":"Cao","year":"2022"},{"key":"B7","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1016\/j.compmedimag.2008.08.003","article-title":"Automatic detection of blue-white veil and related structures in dermoscopy images","volume":"32","author":"Celebi","year":"2008","journal-title":"Comput. Med. Imaging Graph."},{"key":"B8","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.compmedimag.2008.11.002","article-title":"Lesion border detection in dermoscopy images","volume":"33","author":"Celebi","year":"2009","journal-title":"Comput. Med. imaging Graph."},{"key":"B9","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","article-title":"Deeplab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","volume":"40","author":"Chen","year":"2017","journal-title":"IEEE Trans. Pattern Analysis Mach. Intell."},{"key":"B10","article-title":"TransUNet: transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021","journal-title":"arXiv Prepr. arXiv:2102.04306"},{"key":"B11","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/tetci.2023.3309626","article-title":"Transattunet: multi-level attention-guided u-net with transformer for medical image segmentation","volume":"8","author":"Chen","year":"2023","journal-title":"IEEE Trans. Emerg. Top. Comput. Intell."},{"key":"B12","article-title":"On denoising autoencoders trained to minimise binary cross-entropy","author":"Creswell","year":"2017"},{"key":"B13","doi-asserted-by":"publisher","first-page":"102293","DOI":"10.1016\/j.media.2021.102293","article-title":"Ms RED: a novel multi-scale residual encoding and decoding network for skin lesion segmentation","volume":"75","author":"Dai","year":"2022","journal-title":"Med. image Anal."},{"key":"B14","doi-asserted-by":"publisher","first-page":"2420","DOI":"10.1109\/TCBB.2022.3191387","article-title":"Multimodal-boost: multimodal medical image super-resolution using multi-attention network with wavelet transform","volume":"20","author":"Dharejo","year":"2022","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinforma."},{"key":"B15","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"B16","doi-asserted-by":"publisher","first-page":"e252","DOI":"10.1111\/j.1600-0846.2012.00636.x","article-title":"Lesion border detection in dermoscopy images using ensembles of thresholding methods","volume":"19","author":"Emre Celebi","year":"2013","journal-title":"Skin Res. Technol."},{"key":"B17","volume-title":"Pranet: parallel reverse attention network for polyp segmentation: international conference on medical image computing and computer-assisted intervention","author":"Fan","year":"2020"},{"key":"B18","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1111\/brv.12893","article-title":"Bat responses to climate change: a systematic review","volume":"98","author":"Festa","year":"2023","journal-title":"Biol. Rev."},{"key":"B19","first-page":"455","article-title":"A retrospective study on the clinical presentation and treatment outcome of melasma in a tertiary dermatological referral centre in Singapore","volume":"40","author":"Goh","year":"1999","journal-title":"Singap. Med. J."},{"key":"B20","doi-asserted-by":"publisher","first-page":"958","DOI":"10.1016\/s0190-9622(94)70264-0","article-title":"Computer image analysis in the diagnosis of melanoma","volume":"31","author":"Green","year":"1994","journal-title":"J. Am. Acad. Dermatology"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.1001\/archderm.131.12.1453","article-title":"Melasma: etiologic and therapeutic considerations","volume":"131","author":"Grimes","year":"1995","journal-title":"Archives Dermatology"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2281","DOI":"10.1109\/TMI.2019.2903562","article-title":"Ce-net: context encoder network for 2d medical image segmentation","volume":"38","author":"Gu","year":"2019","journal-title":"IEEE Trans. Med. imaging"},{"key":"B23","article-title":"AUCSeg: AUC-oriented pixel-level long-tail semantic segmentation","author":"Han","year":"2024","journal-title":"arXiv Prepr. arXiv:2409.20398"},{"key":"B24","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1111\/bjd.13059","article-title":"Risk factors for facial melasma in women: a case\u2013control study","volume":"171","author":"Handel","year":"2014","journal-title":"Br. J. Dermatology"},{"key":"B25","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR46437.2021.01350","volume-title":"Coordinate attention for efficient mobile network design: proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Hou","year":"2021"},{"key":"B26","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00745","volume-title":"Squeeze-and-excitation networks: proceedings of the IEEE conference on computer vision and pattern recognition","author":"Hu","year":"2018"},{"key":"B27","volume-title":"Unet 3+: a full-scale connected unet for medical image segmentation: ICASSP 2020-2020 IEEE international conference on acoustics, speech and signal processing (ICASSP)","author":"Huang","year":"2020"},{"key":"B28","doi-asserted-by":"publisher","first-page":"977","DOI":"10.1007\/s11045-015-0375-y","article-title":"Hybrid threshold optimization between global image and local regions in image segmentation for melasma severity assessment","volume":"28","author":"Liang","year":"","journal-title":"Multidimensional Syst. Signal Process."},{"key":"B29","doi-asserted-by":"crossref","DOI":"10.1109\/ICDSP.2017.8096129","volume-title":"An improved image segmentation method for melasma severity assessment: 2017 22nd International Conference on Digital Signal Processing (DSP)","author":"Liang","year":""},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.324","volume-title":"Focal loss for dense object detection: proceedings of the IEEE international conference on computer vision","author":"Lin","year":"2017"},{"key":"B31","article-title":"Fully convolutional networks for semantic segmentation: proceedings of the IEEE conference on computer vision and pattern recognition","author":"Long","year":"2015"},{"key":"B32","article-title":"Attention U-Net: learning where to look for the pancreas","author":"Oktay","year":"2018","journal-title":"arXiv Prepr. arXiv:1804.03999"},{"key":"B33","first-page":"62","article-title":"A threshold selection method from gray-level histograms","author":"Otsu","year":"1979"},{"key":"B34","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1016\/s0733-8635(05)70150-9","article-title":"Disorders of hyperpigmentation","volume":"18","author":"Pandya","year":"2000","journal-title":"Dermatol. Clin."},{"key":"B35","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1001\/jama.2011.968","article-title":"Andrews\u2019 diseases of the skin: clinical dermatology","volume":"306","author":"Parish","year":"2011","journal-title":"JAMA"},{"key":"B36","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-00937-3_83","volume-title":"Automatic skin lesion segmentation on dermoscopic images by the means of superpixel merging: international conference on medical image computing and computer-assisted intervention","author":"Pati\u00f1o","year":"2018"},{"key":"B37","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1109\/TBME.2013.2283803","article-title":"Simpler, faster, more accurate melanocytic lesion segmentation through meds","volume":"61","author":"Peruch","year":"2013","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B38","volume-title":"U-net: convolutional networks for biomedical image segmentation: medical image computing and computer-assisted intervention\u2013MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18","author":"Ronneberger","year":"2015"},{"key":"B39","volume-title":"Concurrent spatial and channel \u2018squeeze & excitation\u2019in fully convolutional networks: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2018: 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part I","author":"Roy","year":"2018"},{"key":"B40","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1016\/s0190-9622(81)70071-9","article-title":"Melasma: a clinical, light microscopic, ultrastructural, and immunofluorescence study","volume":"4","author":"Sanchez","year":"1981","journal-title":"J. Am. Acad. Dermatology"},{"key":"B41","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1016\/j.jaad.2011.06.001","article-title":"Melasma: a comprehensive update: part II","volume":"65","author":"Sheth","year":"2011","journal-title":"J. Am. Acad. Dermatology"},{"key":"B42","article-title":"Melasma segmentation using U-Net: a precise approach for skin pigment disorder assessment: 2024 first international conference on electronics, communication and signal processing (ICECSP)","author":"Shilaskar","year":"2024","journal-title":"IEEE"},{"key":"B43","doi-asserted-by":"publisher","first-page":"17","DOI":"10.3322\/caac.21763","article-title":"Cancer statistics, 2023","volume":"73","author":"Siegel","year":"2023","journal-title":"CA Cancer J. Clin."},{"key":"B44","doi-asserted-by":"publisher","first-page":"109524","DOI":"10.1016\/j.patcog.2023.109524","article-title":"MSCA-Net: multi-scale contextual attention network for skin lesion segmentation","volume":"139","author":"Sun","year":"2023","journal-title":"Pattern Recognit."},{"key":"B45","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1111\/j.1468-3083.2011.04430.x","article-title":"Clinical patterns and epidemiological characteristics of facial melasma in Brazilian women","volume":"27","author":"Tamega","year":"2013","journal-title":"J. Eur. Acad. Dermatology Venereol."},{"key":"B46","first-page":"271","article-title":"Epidemiology of skin diseases in people of color","volume":"71","author":"Taylor","year":"2003","journal-title":"Cutis"},{"key":"B47","doi-asserted-by":"publisher","first-page":"501","DOI":"10.3390\/diagnostics11030501","article-title":"ASCU-Net: attention gate, spatial and channel attention u-net for skin lesion segmentation","volume":"11","author":"Tong","year":"2021","journal-title":"Diagnostics"},{"key":"B48","volume-title":"Medical transformer: gated axial-attention for medical image segmentation: medical image computing and computer assisted intervention\u2013MICCAI 2021: 24th international conference, Strasbourg, France, September 27\u2013October 1, 2021, proceedings, part I 24","author":"Valanarasu","year":"2021"},{"key":"B49","volume-title":"SkinNet: a deep learning framework for skin lesion segmentation: 2018 IEEE nuclear science symposium and medical imaging conference proceedings (NSS\/MIC)","author":"Vesal","year":"2018"},{"key":"B50","volume-title":"ECA-Net: efficient channel attention for deep convolutional neural networks: proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Wang","year":"2020"},{"key":"B51","doi-asserted-by":"publisher","first-page":"103870","DOI":"10.1016\/j.bspc.2022.103870","article-title":"DC-net: dual-consistency semi-supervised learning for 3D left atrium segmentation from MRI","volume":"78","author":"Wang","year":"2022","journal-title":"Biomed. Signal Process. Control"},{"key":"B52","volume-title":"Cbam: convolutional block attention module: proceedings of the European conference on computer vision (ECCV)","author":"Woo","year":"2018"},{"key":"B53","doi-asserted-by":"publisher","first-page":"1876","DOI":"10.1109\/TMI.2017.2695227","article-title":"Automatic skin lesion segmentation using deep fully convolutional networks with jaccard distance","volume":"36","author":"Yuan","year":"2017","journal-title":"IEEE Trans. Med. imaging"},{"key":"B54","doi-asserted-by":"publisher","first-page":"972648","DOI":"10.1155\/2011\/972648","article-title":"Automatic segmentation of dermoscopic images by iterative classification","volume":"2011","author":"Zortea","year":"2011","journal-title":"Int. J. Biomed. imaging"}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2025.1665138\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T05:21:43Z","timestamp":1762320103000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2025.1665138\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,5]]},"references-count":54,"alternative-id":["10.3389\/fphys.2025.1665138"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2025.1665138","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,5]]},"article-number":"1665138"}}